3D Semantic Segmentation with KPConv: Live Course
In this Second Chapter of the Live Workshop series, we show how to use KPConv, a very nice 3D Deep Learning Architecture for Semantic Segmentation of 3D Point Clouds. I am thrilled to be joined by Jean-Jacques Ponciano on this one!
I host a live workshop every month, and you can get more info here: https://learngeodata.eu/3d-event-and-...
🍿 NEXT STEPS:
Code a 3D Point Cloud Segmentation Solution with Python: • 3D Point Cloud Segmentation and Shape Reco...
Finish the 3D Tutorial Series: https://learngeodata.eu/3d-tutorials/
Dive in Expert articles: / florentpoux
Become a 3D Data Science Expert: https://learngeodata.eu
🙋 FOLLOW ME
Linkedin: / florent-poux-point-cloud
Github: https://github.com/florentPoux
Research: https://scholar.google.com/citations?...
WHO AM I?
If we haven’t yet before - Hey 👋 I’m Florent, a professor-turned-entrepreneur, and I’ve somehow become one of the most-followed 3D Python Expert. Through my videos here on this channel and my writing, I share evidence-based strategies and tools to help you be better coders and 3D innovators.
📄 CHAPTERS
[00:00:00]: Introduction to 3D Object Detection
[00:02:25]: Mission and Approach
[00:07:55]: Overview of 3D Data Science
[00:11:05]: Setting Up the Environment
[00:13:21]: Data Preparation Phase
[00:16:11]: Data Processing and Concatenation
[00:19:15]: Understanding Intensity in Point Clouds
[00:21:46]: Unsolicited Cases in Deep Learning
[00:27:41]: Training Process with KpConv
[00:38:37]: Results and Inference Time
[00:50:18]: Semantic Implementation Layer
[00:53:00]: Instant Segmentation Wrap-Up